Bedrock Robotics
2027 Internship Behavior Machine Learning Engineer, World Models
San Francisco, CA · On-site · Internship · Posted Sep 10, 2026
- Education
- Currently pursuing a BS, MS, or PhD in computer science, machine learning, robotics, or a related field — or equivalent research or industry experience.
About the job
Train and evaluate world models on real autonomous-machine fleet data, then connect model outputs to planning and control for deployment on excavators.
What you'll do
- Train and evaluate models; run architecture explorations and ablations.
- Build evaluation harnesses and metrics to assess model performance.
- Partner with behavior and controls teams, and present findings.
What they ask for
- Currently pursuing a BS, MS, or PhD in computer science, machine learning, robotics, or a related field — or equivalent research or industry experience.
- Strong Python and hands-on experience training models in PyTorch (or equivalent).
- Ability to read a paper and turn it into a working implementation.
- Comfort with messy real-world data and sound experimental judgment.
Nice to have
- Experience with world models, video prediction, or sequence modeling.
- Background in reinforcement learning or imitation learning; robotics or autonomous vehicle data; or large-scale training infrastructure.
Tools
Python, PyTorch, DreamerV3, V-JEPA 2, Genie 3, GAIA-2, NVIDIA Cosmos
AI focus
Develop and evaluate world models that predict near-future construction-site conditions and inform machine planning and control.
Model-written summary · the original posting is authoritative